aboutsummaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig9
-rw-r--r--mm/backing-dev.c25
-rw-r--r--mm/bootmem.c24
-rw-r--r--mm/highmem.c17
-rw-r--r--mm/ksm.c1
-rw-r--r--mm/memory-failure.c59
-rw-r--r--mm/memory.c14
-rw-r--r--mm/memory_hotplug.c24
-rw-r--r--mm/mempolicy.c13
-rw-r--r--mm/migrate.c2
-rw-r--r--mm/mmap.c4
-rw-r--r--mm/nommu.c6
-rw-r--r--mm/page_alloc.c7
-rw-r--r--mm/percpu.c139
-rw-r--r--mm/swapfile.c3
-rw-r--r--mm/vmscan.c14
16 files changed, 242 insertions, 119 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index 57963c6063d..44cf6f0a3a6 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -67,7 +67,7 @@ config DISCONTIGMEM
config SPARSEMEM
def_bool y
- depends on SPARSEMEM_MANUAL
+ depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL
config FLATMEM
def_bool y
@@ -128,11 +128,8 @@ config SPARSEMEM_VMEMMAP
config MEMORY_HOTPLUG
bool "Allow for memory hot-add"
depends on SPARSEMEM || X86_64_ACPI_NUMA
- depends on HOTPLUG && !(HIBERNATION && !S390) && ARCH_ENABLE_MEMORY_HOTPLUG
- depends on (IA64 || X86 || PPC64 || SUPERH || S390)
-
-comment "Memory hotplug is currently incompatible with Software Suspend"
- depends on SPARSEMEM && HOTPLUG && HIBERNATION && !S390
+ depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG
+ depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
config MEMORY_HOTPLUG_SPARSE
def_bool y
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 5a37e205571..67a33a5a1a9 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -604,15 +604,36 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
/*
* Finally, kill the kernel threads. We don't need to be RCU
- * safe anymore, since the bdi is gone from visibility.
+ * safe anymore, since the bdi is gone from visibility. Force
+ * unfreeze of the thread before calling kthread_stop(), otherwise
+ * it would never exet if it is currently stuck in the refrigerator.
*/
- list_for_each_entry(wb, &bdi->wb_list, list)
+ list_for_each_entry(wb, &bdi->wb_list, list) {
+ wb->task->flags &= ~PF_FROZEN;
kthread_stop(wb->task);
+ }
+}
+
+/*
+ * This bdi is going away now, make sure that no super_blocks point to it
+ */
+static void bdi_prune_sb(struct backing_dev_info *bdi)
+{
+ struct super_block *sb;
+
+ spin_lock(&sb_lock);
+ list_for_each_entry(sb, &super_blocks, s_list) {
+ if (sb->s_bdi == bdi)
+ sb->s_bdi = NULL;
+ }
+ spin_unlock(&sb_lock);
}
void bdi_unregister(struct backing_dev_info *bdi)
{
if (bdi->dev) {
+ bdi_prune_sb(bdi);
+
if (!bdi_cap_flush_forker(bdi))
bdi_wb_shutdown(bdi);
bdi_debug_unregister(bdi);
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 555d5d2731c..d1dc23cc7f1 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -143,6 +143,30 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages);
}
+/*
+ * free_bootmem_late - free bootmem pages directly to page allocator
+ * @addr: starting address of the range
+ * @size: size of the range in bytes
+ *
+ * This is only useful when the bootmem allocator has already been torn
+ * down, but we are still initializing the system. Pages are given directly
+ * to the page allocator, no bootmem metadata is updated because it is gone.
+ */
+void __init free_bootmem_late(unsigned long addr, unsigned long size)
+{
+ unsigned long cursor, end;
+
+ kmemleak_free_part(__va(addr), size);
+
+ cursor = PFN_UP(addr);
+ end = PFN_DOWN(addr + size);
+
+ for (; cursor < end; cursor++) {
+ __free_pages_bootmem(pfn_to_page(cursor), 0);
+ totalram_pages++;
+ }
+}
+
static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
{
int aligned;
diff --git a/mm/highmem.c b/mm/highmem.c
index 25878cc49da..9c1e627f282 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -426,16 +426,21 @@ void __init page_address_init(void)
void debug_kmap_atomic(enum km_type type)
{
- static unsigned warn_count = 10;
+ static int warn_count = 10;
- if (unlikely(warn_count == 0))
+ if (unlikely(warn_count < 0))
return;
if (unlikely(in_interrupt())) {
- if (in_irq()) {
+ if (in_nmi()) {
+ if (type != KM_NMI && type != KM_NMI_PTE) {
+ WARN_ON(1);
+ warn_count--;
+ }
+ } else if (in_irq()) {
if (type != KM_IRQ0 && type != KM_IRQ1 &&
type != KM_BIO_SRC_IRQ && type != KM_BIO_DST_IRQ &&
- type != KM_BOUNCE_READ) {
+ type != KM_BOUNCE_READ && type != KM_IRQ_PTE) {
WARN_ON(1);
warn_count--;
}
@@ -452,7 +457,9 @@ void debug_kmap_atomic(enum km_type type)
}
if (type == KM_IRQ0 || type == KM_IRQ1 || type == KM_BOUNCE_READ ||
- type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ) {
+ type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ ||
+ type == KM_IRQ_PTE || type == KM_NMI ||
+ type == KM_NMI_PTE ) {
if (!irqs_disabled()) {
WARN_ON(1);
warn_count--;
diff --git a/mm/ksm.c b/mm/ksm.c
index bef1af4f77e..5575f8628fe 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1012,6 +1012,7 @@ static struct rmap_item *unstable_tree_search_insert(struct page *page,
struct rmap_item *tree_rmap_item;
int ret;
+ cond_resched();
tree_rmap_item = rb_entry(*new, struct rmap_item, node);
page2[0] = get_mergeable_page(tree_rmap_item);
if (!page2[0])
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 729d4b15b64..dacc6418387 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -35,6 +35,7 @@
#include <linux/mm.h>
#include <linux/page-flags.h>
#include <linux/sched.h>
+#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
@@ -370,9 +371,6 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn)
int ret = FAILED;
struct address_space *mapping;
- if (!isolate_lru_page(p))
- page_cache_release(p);
-
/*
* For anonymous pages we're done the only reference left
* should be the one m_f() holds.
@@ -498,30 +496,18 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn)
*/
static int me_swapcache_dirty(struct page *p, unsigned long pfn)
{
- int ret = FAILED;
-
ClearPageDirty(p);
/* Trigger EIO in shmem: */
ClearPageUptodate(p);
- if (!isolate_lru_page(p)) {
- page_cache_release(p);
- ret = DELAYED;
- }
-
- return ret;
+ return DELAYED;
}
static int me_swapcache_clean(struct page *p, unsigned long pfn)
{
- int ret = FAILED;
-
- if (!isolate_lru_page(p)) {
- page_cache_release(p);
- ret = RECOVERED;
- }
delete_from_swap_cache(p);
- return ret;
+
+ return RECOVERED;
}
/*
@@ -611,8 +597,6 @@ static struct page_state {
{ 0, 0, "unknown page state", me_unknown },
};
-#undef lru
-
static void action_result(unsigned long pfn, char *msg, int result)
{
struct page *page = NULL;
@@ -629,13 +613,16 @@ static int page_action(struct page_state *ps, struct page *p,
unsigned long pfn, int ref)
{
int result;
+ int count;
result = ps->action(p, pfn);
action_result(pfn, ps->msg, result);
- if (page_count(p) != 1 + ref)
+
+ count = page_count(p) - 1 - ref;
+ if (count != 0)
printk(KERN_ERR
"MCE %#lx: %s page still referenced by %d users\n",
- pfn, ps->msg, page_count(p) - 1);
+ pfn, ps->msg, count);
/* Could do more checks here if page looks ok */
/*
@@ -661,12 +648,9 @@ static void hwpoison_user_mappings(struct page *p, unsigned long pfn,
int i;
int kill = 1;
- if (PageReserved(p) || PageCompound(p) || PageSlab(p))
+ if (PageReserved(p) || PageCompound(p) || PageSlab(p) || PageKsm(p))
return;
- if (!PageLRU(p))
- lru_add_drain_all();
-
/*
* This check implies we don't kill processes if their pages
* are in the swap cache early. Those are always late kills.
@@ -738,6 +722,7 @@ static void hwpoison_user_mappings(struct page *p, unsigned long pfn,
int __memory_failure(unsigned long pfn, int trapno, int ref)
{
+ unsigned long lru_flag;
struct page_state *ps;
struct page *p;
int res;
@@ -775,6 +760,24 @@ int __memory_failure(unsigned long pfn, int trapno, int ref)
}
/*
+ * We ignore non-LRU pages for good reasons.
+ * - PG_locked is only well defined for LRU pages and a few others
+ * - to avoid races with __set_page_locked()
+ * - to avoid races with __SetPageSlab*() (and more non-atomic ops)
+ * The check (unnecessarily) ignores LRU pages being isolated and
+ * walked by the page reclaim code, however that's not a big loss.
+ */
+ if (!PageLRU(p))
+ lru_add_drain_all();
+ lru_flag = p->flags & lru;
+ if (isolate_lru_page(p)) {
+ action_result(pfn, "non LRU", IGNORED);
+ put_page(p);
+ return -EBUSY;
+ }
+ page_cache_release(p);
+
+ /*
* Lock the page and wait for writeback to finish.
* It's very difficult to mess with pages currently under IO
* and in many cases impossible, so we just avoid it here.
@@ -790,7 +793,7 @@ int __memory_failure(unsigned long pfn, int trapno, int ref)
/*
* Torn down by someone else?
*/
- if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) {
+ if ((lru_flag & lru) && !PageSwapCache(p) && p->mapping == NULL) {
action_result(pfn, "already truncated LRU", IGNORED);
res = 0;
goto out;
@@ -798,7 +801,7 @@ int __memory_failure(unsigned long pfn, int trapno, int ref)
res = -EBUSY;
for (ps = error_states;; ps++) {
- if ((p->flags & ps->mask) == ps->res) {
+ if (((p->flags | lru_flag)& ps->mask) == ps->res) {
res = page_action(ps, p, pfn, ref);
break;
}
diff --git a/mm/memory.c b/mm/memory.c
index 7e91b5f9f69..6ab19dd4a19 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -641,6 +641,7 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
+ pte_t *orig_src_pte, *orig_dst_pte;
pte_t *src_pte, *dst_pte;
spinlock_t *src_ptl, *dst_ptl;
int progress = 0;
@@ -654,6 +655,8 @@ again:
src_pte = pte_offset_map_nested(src_pmd, addr);
src_ptl = pte_lockptr(src_mm, src_pmd);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
+ orig_src_pte = src_pte;
+ orig_dst_pte = dst_pte;
arch_enter_lazy_mmu_mode();
do {
@@ -677,9 +680,9 @@ again:
arch_leave_lazy_mmu_mode();
spin_unlock(src_ptl);
- pte_unmap_nested(src_pte - 1);
+ pte_unmap_nested(orig_src_pte);
add_mm_rss(dst_mm, rss[0], rss[1]);
- pte_unmap_unlock(dst_pte - 1, dst_ptl);
+ pte_unmap_unlock(orig_dst_pte, dst_ptl);
cond_resched();
if (addr != end)
goto again;
@@ -1820,10 +1823,10 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
token = pmd_pgtable(*pmd);
do {
- err = fn(pte, token, addr, data);
+ err = fn(pte++, token, addr, data);
if (err)
break;
- } while (pte++, addr += PAGE_SIZE, addr != end);
+ } while (addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();
@@ -2539,7 +2542,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
} else if (PageHWPoison(page)) {
ret = VM_FAULT_HWPOISON;
delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
- goto out;
+ goto out_release;
}
lock_page(page);
@@ -2611,6 +2614,7 @@ out_nomap:
pte_unmap_unlock(page_table, ptl);
out_page:
unlock_page(page);
+out_release:
page_cache_release(page);
return ret;
}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 821dee59637..2047465cd27 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -26,6 +26,7 @@
#include <linux/migrate.h>
#include <linux/page-isolation.h>
#include <linux/pfn.h>
+#include <linux/suspend.h>
#include <asm/tlbflush.h>
@@ -447,7 +448,8 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
}
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
-static pg_data_t *hotadd_new_pgdat(int nid, u64 start)
+/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
+static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
{
struct pglist_data *pgdat;
unsigned long zones_size[MAX_NR_ZONES] = {0};
@@ -484,14 +486,18 @@ int __ref add_memory(int nid, u64 start, u64 size)
struct resource *res;
int ret;
+ lock_system_sleep();
+
res = register_memory_resource(start, size);
+ ret = -EEXIST;
if (!res)
- return -EEXIST;
+ goto out;
if (!node_online(nid)) {
pgdat = hotadd_new_pgdat(nid, start);
+ ret = -ENOMEM;
if (!pgdat)
- return -ENOMEM;
+ goto out;
new_pgdat = 1;
}
@@ -514,7 +520,8 @@ int __ref add_memory(int nid, u64 start, u64 size)
BUG_ON(ret);
}
- return ret;
+ goto out;
+
error:
/* rollback pgdat allocation and others */
if (new_pgdat)
@@ -522,6 +529,8 @@ error:
if (res)
release_memory_resource(res);
+out:
+ unlock_system_sleep();
return ret;
}
EXPORT_SYMBOL_GPL(add_memory);
@@ -758,6 +767,8 @@ int offline_pages(unsigned long start_pfn,
if (!test_pages_in_a_zone(start_pfn, end_pfn))
return -EINVAL;
+ lock_system_sleep();
+
zone = page_zone(pfn_to_page(start_pfn));
node = zone_to_nid(zone);
nr_pages = end_pfn - start_pfn;
@@ -765,7 +776,7 @@ int offline_pages(unsigned long start_pfn,
/* set above range as isolated */
ret = start_isolate_page_range(start_pfn, end_pfn);
if (ret)
- return ret;
+ goto out;
arg.start_pfn = start_pfn;
arg.nr_pages = nr_pages;
@@ -843,6 +854,7 @@ repeat:
writeback_set_ratelimit();
memory_notify(MEM_OFFLINE, &arg);
+ unlock_system_sleep();
return 0;
failed_removal:
@@ -852,6 +864,8 @@ failed_removal:
/* pushback to free area */
undo_isolate_page_range(start_pfn, end_pfn);
+out:
+ unlock_system_sleep();
return ret;
}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 7dd9d9f8069..4545d594424 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1024,7 +1024,7 @@ static long do_mbind(unsigned long start, unsigned long len,
err = migrate_prep();
if (err)
- return err;
+ goto mpol_out;
}
{
NODEMASK_SCRATCH(scratch);
@@ -1039,10 +1039,9 @@ static long do_mbind(unsigned long start, unsigned long len,
err = -ENOMEM;
NODEMASK_SCRATCH_FREE(scratch);
}
- if (err) {
- mpol_put(new);
- return err;
- }
+ if (err)
+ goto mpol_out;
+
vma = check_range(mm, start, end, nmask,
flags | MPOL_MF_INVERT, &pagelist);
@@ -1058,9 +1057,11 @@ static long do_mbind(unsigned long start, unsigned long len,
if (!err && nr_failed && (flags & MPOL_MF_STRICT))
err = -EIO;
- }
+ } else
+ putback_lru_pages(&pagelist);
up_write(&mm->mmap_sem);
+ mpol_out:
mpol_put(new);
return err;
}
diff --git a/mm/migrate.c b/mm/migrate.c
index 1a4bf481378..7dbcb22316d 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -602,7 +602,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
struct page *newpage = get_new_page(page, private, &result);
int rcu_locked = 0;
int charge = 0;
- struct mem_cgroup *mem;
+ struct mem_cgroup *mem = NULL;
if (!newpage)
return -ENOMEM;
diff --git a/mm/mmap.c b/mm/mmap.c
index 73f5e4b6401..292ddc3cef9 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -20,7 +20,6 @@
#include <linux/fs.h>
#include <linux/personality.h>
#include <linux/security.h>
-#include <linux/ima.h>
#include <linux/hugetlb.h>
#include <linux/profile.h>
#include <linux/module.h>
@@ -1061,9 +1060,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
error = security_file_mmap(file, reqprot, prot, flags, addr, 0);
if (error)
return error;
- error = ima_file_mmap(file, prot);
- if (error)
- return error;
return mmap_region(file, addr, len, flags, vm_flags, pgoff);
}
diff --git a/mm/nommu.c b/mm/nommu.c
index 5189b5aed8c..9876fa0c3ad 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1362,9 +1362,11 @@ share:
error_just_free:
up_write(&nommu_region_sem);
error:
- fput(region->vm_file);
+ if (region->vm_file)
+ fput(region->vm_file);
kmem_cache_free(vm_region_jar, region);
- fput(vma->vm_file);
+ if (vma->vm_file)
+ fput(vma->vm_file);
if (vma->vm_flags & VM_EXECUTABLE)
removed_exe_file_vma(vma->vm_mm);
kmem_cache_free(vm_area_cachep, vma);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index bf720550b44..2bc2ac63f41 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1769,7 +1769,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
* See also cpuset_zone_allowed() comment in kernel/cpuset.c.
*/
alloc_flags &= ~ALLOC_CPUSET;
- } else if (unlikely(rt_task(p)))
+ } else if (unlikely(rt_task(p)) && !in_interrupt())
alloc_flags |= ALLOC_HARDER;
if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
@@ -1817,9 +1817,9 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
goto nopage;
+restart:
wake_all_kswapd(order, zonelist, high_zoneidx);
-restart:
/*
* OK, we're below the kswapd watermark and have kicked background
* reclaim. Now things get more complex, so set up alloc_flags according
@@ -2183,7 +2183,7 @@ void show_free_areas(void)
printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n"
" active_file:%lu inactive_file:%lu isolated_file:%lu\n"
" unevictable:%lu"
- " dirty:%lu writeback:%lu unstable:%lu buffer:%lu\n"
+ " dirty:%lu writeback:%lu unstable:%lu\n"
" free:%lu slab_reclaimable:%lu slab_unreclaimable:%lu\n"
" mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n",
global_page_state(NR_ACTIVE_ANON),
@@ -2196,7 +2196,6 @@ void show_free_areas(void)
global_page_state(NR_FILE_DIRTY),
global_page_state(NR_WRITEBACK),
global_page_state(NR_UNSTABLE_NFS),
- nr_blockdev_pages(),
global_page_state(NR_FREE_PAGES),
global_page_state(NR_SLAB_RECLAIMABLE),
global_page_state(NR_SLAB_UNRECLAIMABLE),
diff --git a/mm/percpu.c b/mm/percpu.c
index 6af78c1ee70..5adfc268b40 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -153,7 +153,10 @@ static int pcpu_reserved_chunk_limit;
*
* During allocation, pcpu_alloc_mutex is kept locked all the time and
* pcpu_lock is grabbed and released as necessary. All actual memory
- * allocations are done using GFP_KERNEL with pcpu_lock released.
+ * allocations are done using GFP_KERNEL with pcpu_lock released. In
+ * general, percpu memory can't be allocated with irq off but
+ * irqsave/restore are still used in alloc path so that it can be used
+ * from early init path - sched_init() specifically.
*
* Free path accesses and alters only the index data structures, so it
* can be safely called from atomic context. When memory needs to be
@@ -352,62 +355,86 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
}
/**
- * pcpu_extend_area_map - extend area map for allocation
- * @chunk: target chunk
+ * pcpu_need_to_extend - determine whether chunk area map needs to be extended
+ * @chunk: chunk of interest
*
- * Extend area map of @chunk so that it can accomodate an allocation.
- * A single allocation can split an area into three areas, so this
- * function makes sure that @chunk->map has at least two extra slots.
+ * Determine whether area map of @chunk needs to be extended to
+ * accomodate a new allocation.
*
* CONTEXT:
- * pcpu_alloc_mutex, pcpu_lock. pcpu_lock is released and reacquired
- * if area map is extended.
+ * pcpu_lock.
*
* RETURNS:
- * 0 if noop, 1 if successfully extended, -errno on failure.
+ * New target map allocation length if extension is necessary, 0
+ * otherwise.
*/
-static int pcpu_extend_area_map(struct pcpu_chunk *chunk)
+static int pcpu_need_to_extend(struct pcpu_chunk *chunk)
{
int new_alloc;
- int *new;
- size_t size;
- /* has enough? */
if (chunk->map_alloc >= chunk->map_used + 2)
return 0;
- spin_unlock_irq(&pcpu_lock);
-
new_alloc = PCPU_DFL_MAP_ALLOC;
while (new_alloc < chunk->map_used + 2)
new_alloc *= 2;
- new = pcpu_mem_alloc(new_alloc * sizeof(new[0]));
- if (!new) {
- spin_lock_irq(&pcpu_lock);
+ return new_alloc;
+}
+
+/**
+ * pcpu_extend_area_map - extend area map of a chunk
+ * @chunk: chunk of interest
+ * @new_alloc: new target allocation length of the area map
+ *
+ * Extend area map of @chunk to have @new_alloc entries.
+ *
+ * CONTEXT:
+ * Does GFP_KERNEL allocation. Grabs and releases pcpu_lock.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
+{
+ int *old = NULL, *new = NULL;
+ size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
+ unsigned long flags;
+
+ new = pcpu_mem_alloc(new_size);
+ if (!new)
return -ENOMEM;
- }
- /*
- * Acquire pcpu_lock and switch to new area map. Only free
- * could have happened inbetween, so map_used couldn't have
- * grown.
- */
- spin_lock_irq(&pcpu_lock);
- BUG_ON(new_alloc < chunk->map_used + 2);
+ /* acquire pcpu_lock and switch to new area map */
+ spin_lock_irqsave(&pcpu_lock, flags);
+
+ if (new_alloc <= chunk->map_alloc)
+ goto out_unlock;
- size = chunk->map_alloc * sizeof(chunk->map[0]);
- memcpy(new, chunk->map, size);
+ old_size = chunk->map_alloc * sizeof(chunk->map[0]);
+ memcpy(new, chunk->map, old_size);
/*
* map_alloc < PCPU_DFL_MAP_ALLOC indicates that the chunk is
* one of the first chunks and still using static map.
*/
if (chunk->map_alloc >= PCPU_DFL_MAP_ALLOC)
- pcpu_mem_free(chunk->map, size);
+ old = chunk->map;
chunk->map_alloc = new_alloc;
chunk->map = new;
+ new = NULL;
+
+out_unlock:
+ spin_unlock_irqrestore(&pcpu_lock, flags);
+
+ /*
+ * pcpu_mem_free() might end up calling vfree() which uses
+ * IRQ-unsafe lock and thus can't be called under pcpu_lock.
+ */
+ pcpu_mem_free(old, old_size);
+ pcpu_mem_free(new, new_size);
+
return 0;
}
@@ -1046,7 +1073,8 @@ static void *pcpu_alloc(size_t size, size_t align, bool reserved)
static int warn_limit = 10;
struct pcpu_chunk *chunk;
const char *err;
- int slot, off;
+ int slot, off, new_alloc;
+ unsigned long flags;
if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
WARN(true, "illegal size (%zu) or align (%zu) for "
@@ -1055,19 +1083,30 @@ static void *pcpu_alloc(size_t size, size_t align, bool reserved)
}
mutex_lock(&pcpu_alloc_mutex);
- spin_lock_irq(&pcpu_lock);
+ spin_lock_irqsave(&pcpu_lock, flags);
/* serve reserved allocations from the reserved chunk if available */
if (reserved && pcpu_reserved_chunk) {
chunk = pcpu_reserved_chunk;
- if (size > chunk->contig_hint ||
- pcpu_extend_area_map(chunk) < 0) {
- err = "failed to extend area map of reserved chunk";
+
+ if (size > chunk->contig_hint) {
+ err = "alloc from reserved chunk failed";
goto fail_unlock;
}
+
+ while ((new_alloc = pcpu_need_to_extend(chunk))) {
+ spin_unlock_irqrestore(&pcpu_lock, flags);
+ if (pcpu_extend_area_map(chunk, new_alloc) < 0) {
+ err = "failed to extend area map of reserved chunk";
+ goto fail_unlock_mutex;
+ }
+ spin_lock_irqsave(&pcpu_lock, flags);
+ }
+
off = pcpu_alloc_area(chunk, size, align);
if (off >= 0)
goto area_found;
+
err = "alloc from reserved chunk failed";
goto fail_unlock;
}
@@ -1079,14 +1118,20 @@ restart:
if (size > chunk->contig_hint)
continue;
- switch (pcpu_extend_area_map(chunk)) {
- case 0:
- break;
- case 1:
- goto restart; /* pcpu_lock dropped, restart */
- default:
- err = "failed to extend area map";
- goto fail_unlock;
+ new_alloc = pcpu_need_to_extend(chunk);
+ if (new_alloc) {
+ spin_unlock_irqrestore(&pcpu_lock, flags);
+ if (pcpu_extend_area_map(chunk,
+ new_alloc) < 0) {
+ err = "failed to extend area map";
+ goto fail_unlock_mutex;
+ }
+ spin_lock_irqsave(&pcpu_lock, flags);
+ /*
+ * pcpu_lock has been dropped, need to
+ * restart cpu_slot list walking.
+ */
+ goto restart;
}
off = pcpu_alloc_area(chunk, size, align);
@@ -1096,7 +1141,7 @@ restart:
}
/* hmmm... no space left, create a new chunk */
- spin_unlock_irq(&pcpu_lock);
+ spin_unlock_irqrestore(&pcpu_lock, flags);
chunk = alloc_pcpu_chunk();
if (!chunk) {
@@ -1104,16 +1149,16 @@ restart:
goto fail_unlock_mutex;
}
- spin_lock_irq(&pcpu_lock);
+ spin_lock_irqsave(&pcpu_lock, flags);
pcpu_chunk_relocate(chunk, -1);
goto restart;
area_found:
- spin_unlock_irq(&pcpu_lock);
+ spin_unlock_irqrestore(&pcpu_lock, flags);
/* populate, map and clear the area */
if (pcpu_populate_chunk(chunk, off, size)) {
- spin_lock_irq(&pcpu_lock);
+ spin_lock_irqsave(&pcpu_lock, flags);
pcpu_free_area(chunk, off);
err = "failed to populate";
goto fail_unlock;
@@ -1125,7 +1170,7 @@ area_found:
return __addr_to_pcpu_ptr(chunk->base_addr + off);
fail_unlock:
- spin_unlock_irq(&pcpu_lock);
+ spin_unlock_irqrestore(&pcpu_lock, flags);
fail_unlock_mutex:
mutex_unlock(&pcpu_alloc_mutex);
if (warn_limit) {
diff --git a/mm/swapfile.c b/mm/swapfile.c
index a1bc6b9af9a..9c590eef791 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1151,8 +1151,7 @@ static int try_to_unuse(unsigned int type)
} else
retval = unuse_mm(mm, entry, page);
- if (set_start_mm &&
- swap_count(*swap_map) < swcount) {
+ if (set_start_mm && *swap_map < swcount) {
mmput(new_start_mm);
atomic_inc(&mm->mm_users);
new_start_mm = mm;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 64e43889883..777af57fd8c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -544,6 +544,16 @@ redo:
*/
lru = LRU_UNEVICTABLE;
add_page_to_unevictable_list(page);
+ /*
+ * When racing with an mlock clearing (page is
+ * unlocked), make sure that if the other thread does
+ * not observe our setting of PG_lru and fails
+ * isolation, we see PG_mlocked cleared below and move
+ * the page back to the evictable list.
+ *
+ * The other side is TestClearPageMlocked().
+ */
+ smp_mb();
}
/*
@@ -1088,7 +1098,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
int lumpy_reclaim = 0;
while (unlikely(too_many_isolated(zone, file, sc))) {
- congestion_wait(WRITE, HZ/10);
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
/* We are about to die and free our memory. Return now. */
if (fatal_signal_pending(current))
@@ -1356,7 +1366,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
* IO, plus JVM can create lots of anon VM_EXEC pages,
* so we ignore them here.
*/
- if ((vm_flags & VM_EXEC) && !PageAnon(page)) {
+ if ((vm_flags & VM_EXEC) && page_is_file_cache(page)) {
list_add(&page->lru, &l_active);
continue;
}